Instructions to use Ghaxalll/ghaxal-face-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Ghaxalll/ghaxal-face-v3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("krea/Krea-2-Raw", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Ghaxalll/ghaxal-face-v3") prompt = "ghaxal_woman, sitting at a desk by a window, soft even daylight, no harsh shadows, 85mm, natural skin texture, calm neutral expression" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Krea 2 LoRA โ Ghaxalll/ghaxal-face-v3

- Prompt
- ghaxal_woman, sitting at a desk by a window, soft even daylight, no harsh shadows, 85mm, natural skin texture, calm neutral expression

- Prompt
- ghaxal_woman, close portrait against a plain wall, soft overcast light, no sunglasses, relaxed face, 50mm

- Prompt
- ghaxal_woman, full body, standing against a plain turquoise tiled wall, structural black outfit, soft even light, editorial fashion photograph
A DreamBooth-LoRA for Krea 2, trained on Krea 2 RAW and shown on Krea 2 Turbo. The samples below were generated with this LoRA on Turbo (8 steps).
Trigger
Use the token ghaxal_woman to invoke the concept.
Samples
"ghaxal_woman, sitting at a desk by a window, soft even daylight, no harsh shadows, 85mm, natural skin texture, calm neutral expression"
"ghaxal_woman, close portrait against a plain wall, soft overcast light, no sunglasses, relaxed face, 50mm"
"ghaxal_woman, full body, standing against a plain turquoise tiled wall, structural black outfit, soft even light, editorial fashion photograph"
Use it with diffusers
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("Ghaxalll/ghaxal-face-v3")
image = pipe("ghaxal_woman, sitting at a desk by a window, soft even daylight, no harsh shadows, 85mm, natural skin texture, calm neutral expression", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
- Downloads last month
- 6
Model tree for Ghaxalll/ghaxal-face-v3
Base model
krea/Krea-2-Raw

